Trading through Earnings Seasons using Self-Supervised Contrastive Representation Learning

TL;DR

This paper introduces CET, a self-supervised contrastive learning model that enhances stock prediction by effectively utilizing earnings data despite its irregular release cycle and rapid relevance decay.

Contribution

The paper presents CET, a novel contrastive predictive coding-based model that improves the use of earnings data in medium-frequency trading algorithms, outperforming benchmark models.

Findings

CET demonstrates superior ability to extrapolate earnings data over time.

CET maintains prediction accuracy despite the rapid decay of earnings relevance.

The model performs well across diverse sectors.

Abstract

Earnings release is a key economic event in the financial markets and crucial for predicting stock movements. Earnings data gives a glimpse into how a company is doing financially and can hint at where its stock might go next. However, the irregularity of its release cycle makes it a challenge to incorporate this data in a medium-frequency algorithmic trading model and the usefulness of this data fades fast after it is released, making it tough for models to stay accurate over time. Addressing this challenge, we introduce the Contrastive Earnings Transformer (CET) model, a self-supervised learning approach rooted in Contrastive Predictive Coding (CPC), aiming to optimise the utilisation of earnings data. To ascertain its effectiveness, we conduct a comparative study of CET against benchmark models across diverse sectors. Our research delves deep into the intricacies of stock data, evaluating how various models, and notably CET, handle the rapidly changing relevance of earnings data over time and over different sectors. The research outcomes shed light on CET's distinct advantage in extrapolating the inherent value of earnings data over time. Its foundation on CPC allows for a nuanced understanding, facilitating consistent stock predictions even as the earnings data ages. This finding about CET presents a fresh approach to better use earnings data in algorithmic trading for predicting stock price trends.